Student or educator? Sign up with your school email and get 6 months of Pro free.
Cited by 725Machine Learning in Materials SciencePerovskite Materials and ApplicationsAdvanced Chemical Physics Studies

The DOI matches its Crossref record; 56 of the 56 references it cites were found in a registry or an index.

Accelerated discovery of stable lead-free hybrid organic-inorganic perovskites via machine learning

Open access

Abstract

Rapidly discovering functional materials remains an open challenge because the traditional trial-and-error methods are usually inefficient especially when thousands of candidates are treated. Here, we develop a target-driven method to predict undiscovered hybrid organic-inorganic perovskites (HOIPs) for photovoltaics. This strategy, combining machine learning techniques and density functional theory calculations, aims to quickly screen the HOIPs based on bandgap and solve the problems of toxicity and poor environmental stability in HOIPs. Successfully, six orthorhombic lead-free HOIPs with proper bandgap for solar cells and room temperature thermal stability are screened out from 5158 unexplored HOIPs and two of them stand out with direct bandgaps in the visible region and excellent environmental stability. Essentially, a close structure-property relationship mapping the HOIPs bandgap is established. Our method can achieve high accuracy in a flash and be applicable to a broad class of functional material design.

Overview

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Integrity signals

Registry

Crossref · 10.1038/s41467-018-05761-w

Cites

56 of 56 references verified0 citation errors · 0 not checkable

Statistics

Figures

Fig. 1 Lead-free HOIPs design framework. The material design framework combined with ML and DFT to efficiently search for stable Pb-free HOIPs with proper bandgap. The blue boxes represent the material screening process based on the ML algorithm generated from historical HOIP data. Then electronic properties and stability evaluation of these selected candidates are further calculated using DFT, which are shown in the green boxes
Fig. 1 Lead-free HOIPs design framework. The material design framework combined with ML and DFT to efficiently search for stable Pb-free HOIPs with proper bandgap. The blue boxes represent the material screening process based on the ML algorithm generated from historical HOIP data. Then electronic properties and stability evaluation of these selected candidates are further calculated using DFT, which are shown in the green boxesCC BY · PubMed Central
Fig. 2 HOIPs input dataset for training and testing. a 212 high throughput HOIP structures. The combination of 11 small organic molecular species (A-site) and 32 divalent metals (B-site) constitutes the input samples of our ML model. X is a typical halide. b Data visualization in training (blue dots) and test (red dots) of tolerance factor and bandgap Eg^PBE of HOIPs. The entire dataset consists of metals, semiconductors, and insulators
Fig. 2 HOIPs input dataset for training and testing. a 212 high throughput HOIP structures. The combination of 11 small organic molecular species (A-site) and 32 divalent metals (B-site) constitutes the input samples of our ML model. X is a typical halide. b Data visualization in training (blue dots) and test (red dots) of tolerance factor and bandgap Eg^PBE of HOIPs. The entire dataset consists of metals, semiconductors, and insulatorsCC BY · PubMed Central
Fig. 3 Importance and correlation of the selected features. a The 14 selected features are ranked using GBR algorithm. b The heat map of Pearson correlation coefficient matrix among the selected features for HOIPs
Fig. 3 Importance and correlation of the selected features. a The 14 selected features are ranked using GBR algorithm. b The heat map of Pearson correlation coefficient matrix among the selected features for HOIPsCC BY · PubMed Central
Fig. 4 Results and insights from ML model. a The fitting results of test bandgaps Eg^PBE and predicted bandgaps Eg^ML. Coefficient of determination (R2), Pearson coefficient (r) and mean squared error (MSE) are computed to estimate the prediction errors. The subplot is the convergence of model accuracy for five cross-validation split of the data. b Scatter plots of tolerance factors against the bandgaps for the prediction dataset from trained ML model (blue, red and dark gray plots represent train, test and prediction set, respectively). Data visualization of predicted bandgaps for all possible HOIPs (one color represents a class of halogen perovskites) with (c) tolerance factor, (d) octahedral factor, (e) ionic polarizability for the A-site ions, and (f) electronegativity of B-site ions. The dotted box represents the most appropriate range for each feature
Fig. 4 Results and insights from ML model. a The fitting results of test bandgaps Eg^PBE and predicted bandgaps Eg^ML. Coefficient of determination (R2), Pearson coefficient (r) and mean squared error (MSE) are computed to estimate the prediction errors. The subplot is the convergence of model accuracy for five cross-validation split of the data. b Scatter plots of tolerance factors against the bandgaps for the prediction dataset from trained ML model (blue, red and dark gray plots represent train, test and prediction set, respectively). Data visualization of predicted bandgaps for all possible HOIPs (one color represents a class of halogen perovskites) with (c) tolerance factor, (d) octahedral factor, (e) ionic polarizability for the A-site ions, and (f) electronegativity of B-site ions. The dotted box represents the most appropriate range for each featureCC BY · PubMed Central
Fig. 5 Comparison with DFT calculations. a A comparison between ML-predicted and DFT-calculated results of six selected HOIPs. b Optimized structures, c band structures, d projected density of states (PDOS), e total energy during 5 ps AIMD simulations for C2H5OSnBr3 and C2H6NSnBr3 at 300 K. The subplots in d are the PDOS near the Fermi level
Fig. 5 Comparison with DFT calculations. a A comparison between ML-predicted and DFT-calculated results of six selected HOIPs. b Optimized structures, c band structures, d projected density of states (PDOS), e total energy during 5 ps AIMD simulations for C2H5OSnBr3 and C2H6NSnBr3 at 300 K. The subplots in d are the PDOS near the Fermi levelCC BY · PubMed Central

Verification

Claims the paper makes

The claims and statistics of this paper haven’t been checked yet.

Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.

A few free checks a day · papers already verified open instantly · results are public

Self-check

Percentages, sums and reported differences re-computed from the paper’s own numbers.

The self-check needs the paper’s full text.

Citations

Cites

Show all 56 references

Research works printed but not linked: 2

  1. Boser, B. E., Guyon, I. M. & Vapnik, V. N. Proceedings of the Fifth Annual ACM Workshop on Computational Learning Theory (ACM Press, New York, 1992)
  2. Nasrabadi, N. M. Pattern Recognition and Machine Learning CH. vol. 14 (Springer Press, New York, 2016).

Cited by

See all 725

Metadata

Authors
Lu, S., Zhou, Q., Ouyang, Y., Guo, Y., Li, Q., & Wang, J.
Affiliations
Southeast University (CN)
Corresponding author
Wang, Jinlan
Venue
Nature Communications
Published
2018-08-24
Volume
9
Issue
1
Pages
3405-3405
ISSN
2041-1723 (ISSN-L)
OpenAlex
W2888395196
Cited by
725
References
56
Citations by year
2026: 60 · 2025: 119 · 2024: 105 · 2023: 90 · 2022: 107 · 2021: 114 · 2020: 75 · 2019: 48 · 2018: 7
FWCI
22.77
Type
journal article
Language
en
Open access
Licence
Locations
  • Nature Communications (publishedVersion, cc-by)
  • Europe PMC (PubMed Central) (publishedVersion, cc-by)
  • PubMed Central (publishedVersion, cc-by)
  • PubMed (publishedVersion)
  • RePEc: Research Papers in Economics (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion)
  • DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
Funders
  • National Natural Science Foundation of China (2017YFA0204800, 21525311, 21773027)
  • National Key Research and Development Program of China (2017YFA0204800)
  • Fundamental Research Funds for the Central Universities (Jiangsu 333, 21773027)
  • National Supercomputing Center of Tianjin
  • National Supercomputing Center, Korea Institute of Science and Technology Information
Topics
  • Physical Sciences › Materials Science › Materials Chemistry › Machine Learning in Materials Science
  • Physical Sciences › Engineering › Electrical and Electronic Engineering › Perovskite Materials and Applications
  • Physical Sciences › Physics and Astronomy › Atomic and Molecular Physics, and Optics › Advanced Chemical Physics Studies
Keywords
perovskite solar cells, band gap prediction, structure-property relationships, environmental stability, thermal stability, toxicity, orthorhombic perovskite, materials screening, machine learning

About these checks

Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.

Statistics and arithmetic are recomputed, not judged.

Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.

What counts as a claim ›How we measure confidence ›How we check this ›

Are you an author, or do you see a problem with this page? Request a review

How to cite

Cite CoChat for the checks on this page, and the paper for its own findings.

This page
CoChat. (2026). Citation check: Accelerated discovery of stable lead-free hybrid organic-inorganic perovskites via machine learning. https://app.cochat.ai/papers/10.1038/s41467-018-05761-w
The paper
Lu, S., Zhou, Q., Ouyang, Y., Guo, Y., Li, Q., & Wang, J. (2018). Accelerated discovery of stable lead-free hybrid organic-inorganic perovskites via machine learning. Nature Communications. https://doi.org/10.1038/s41467-018-05761-w

Data sources

Bibliographic data: Semantic Scholar, OpenAlex, Crossref.

Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).

Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.